Lloyds Banking Group has carried out an experiment into how quantum computing could help to identify money mules, it announced Tuesday.

The bank said the experiment “marks a major step” in building the skills and technology needed to tackle economic crime in the future.

Conducted in partnership with IBM, the experiment tested multiple quantum algorithms to see whether patterns of known money mule behaviours could be identified within a larger transactional graph.

It is the first known application of a quantum optimisation algorithm to detect money mule accounts using anonymised real-world transaction data on actual quantum hardware, according to the bank.

The experiment successfully identified a real money mule that had been deliberately embedded in the data to validate the approach, which Lloyds said demonstrated how real-world financial crime challenges could be tackled in the future using algorithms running on quantum computers.

The bank said money mule networks – where criminal behaviour is hidden within vast webs of legitimate transactions – are a significant enabler of scams and fraud. It added that insights from this experiment could one day help banks detect sophisticated fraud earlier, better protecting their customers.

Lloyds created a working group of quantum ambassadors – including specialists in physics, maths and computer science from across the business – to manage the experiment.

Over the nine-month project, this team worked alongside Lloyds’ economic crime prevention experts and IBM’s specialists to explore how quantum computing could be used to uncover complex fraud patterns that can be challenging for traditional computers to detect.

“Financial crime is becoming more complex and more network driven, which means we need to keep pushing the boundaries of technology to protect customers,” said Ron van Kemenade, chief operating officer at Lloyds Banking Group. “While quantum computing is still emerging, this experiment has allowed us to translate research into practical insights, while building a strong internal community of quantum experts that will continue to explore future use cases and applications as the technology evolves.”

The work was carried out on IBM’s Quantum Heron device, using 152 of its 156 available qubits.

Traditional computers process information as bits that are either a 0 or a 1. Quantum computers use qubits, which follow the rules of quantum physics and allow systems to represent many states simultaneously.

As a result, a quantum computer can perform certain computations beyond the capabilities of a traditional computer by assessing all possible answers to a problem simultaneously before deciding on the most optimal. A traditional computer would have to solve each potential answer linearly, which could be far slower depending on the size of the problem.

---